GPU Power Architect - New College Grad 2026
NVIDIAJob Title
GPU Power Architect - New College Grad 2026
Role Summary
Join NVIDIA's Applied Power Architecture team to develop power estimation models, tools, and analyses for datacenter GPUs and systems. The role focuses on improving energy efficiency and Perf/Watt across GPU products and multi‑GPU datacenter platforms.
The position involves architecture exploration, performance-vs-power tradeoff analysis, and building data-driven models to guide hardware and system-level power optimizations.
Experience Level
Entry-level — targeted to new college graduates (new grads / recent graduates).
Responsibilities
Key responsibilities include modeling, analysis, and tool development to evaluate and improve power and performance across GPUs and systems.
- Develop and contribute to power estimation models and tools for GPUs and systems (e.g., DGX).
- Perform early GPU and system architecture exploration focused on energy efficiency and total cost of ownership.
- Conduct performance vs. power analyses across future product lineups.
- Apply machine learning techniques to build accurate power and performance models for GPUs, CPUs, switches, and platforms.
- Analyze workload characteristics for GenAI and HPC at datacenter scale (multi-GPU) to inform HW/SW feature decisions.
- Model and analyze high-speed, high-density interconnect technologies.
Requirements
Must-have technical skills and experience for successful candidates.
- Knowledge of energy-efficient chip design fundamentals and tradeoffs.
- Familiarity with low-power design techniques: multi-VT, clock gating, power gating, DVFS.
- Understanding of processor and system-software architectures and their performance/power modeling techniques (GPU experience is a plus).
- Proficiency in Python and data analysis libraries such as Pandas and NumPy; experience with PyTorch or similar frameworks.
- Familiarity with performance monitors and architectural simulators used in modern processors.
- Strong analytical and data-driven problem-solving skills.
- Nice-to-have: experience applying machine learning to modeling tasks and prior exposure to datacenter-scale workloads.
Education Requirements
Pursuing or recently completed a Bachelor's or Master's degree in Electrical Engineering, Computer Engineering, or a closely related field — or equivalent practical experience. (The posting explicitly references Bachelor's or Master's degrees; equivalent experience is acceptable.)
About the Company
Company: NVIDIA
Headquarters: Santa Clara, California, USA
NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.
